paper-slides
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
82
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly specifies concrete outputs (beamer LaTeX PDF, PPTX, speaker notes, talk script), defines the input context (compiled paper for conference), and provides comprehensive bilingual trigger terms. It follows third-person voice and has a well-structured 'Use when' clause that covers both Chinese and English user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate conference presentation slides, produce beamer LaTeX → PDF + editable PPTX, create speaker notes, and generate a full talk script from a compiled paper. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate conference presentation slides with beamer LaTeX → PDF + PPTX, speaker notes, and talk script from a compiled paper) and 'when' (explicit 'Use when' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '做PPT', '做幻灯片', 'make slides', 'conference talk', 'presentation slides', '生成slides', '写演讲稿', 'beamer slides'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: focuses specifically on conference presentations from compiled papers using beamer LaTeX, which is a clear niche. The combination of academic context, beamer format, and bilingual triggers makes it unlikely to conflict with generic presentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable and has excellent workflow clarity with well-defined phases, checkpoints, and error recovery. However, it is severely over-verbose — the full LaTeX template, complete talk script template with 8 Q&A placeholders, venue color tables, and detailed slide-by-slide outlines for every talk type massively inflate the token count with content Claude could generate independently. The monolithic structure would benefit from splitting templates and reference tables into separate files.
Suggestions
Move the full LaTeX beamer template, talk script template, and PPTX generation script details into separate referenced files (e.g., BEAMER_TEMPLATE.tex, SCRIPT_TEMPLATE.md) to reduce the main skill file size by ~50%.
Remove the verbose Q&A section template (8 placeholder questions) — Claude can generate contextually appropriate Q&A from the paper without being shown a format template.
Condense the slide outline tables for each talk type into a compact format (e.g., just slide count ranges and key sections) rather than full per-slide breakdowns — Claude can determine appropriate slide content from the paper structure.
Remove explanatory rationale text like 'Unlike posters (single page, visual-first), slides tell a temporal story' — Claude already understands the difference between slides and posters.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Includes extensive template content Claude could generate on its own (full LaTeX templates, full talk script templates, Q&A templates with 8 placeholder questions, venue color tables). The slide outline tables for each talk type, the full beamer template, and the complete talk script format are all things Claude can produce without being shown verbatim examples. Much of this could be condensed to key rules and constraints. | 1 / 3 |
Actionability | Highly actionable with executable bash commands, complete LaTeX templates, specific python-pptx usage, concrete compilation commands, and explicit error handling loops. Every phase has copy-paste ready commands and clear outputs. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-8) with explicit checkpoints, state persistence via SLIDES_STATE.json, error handling loops (max 3 compile attempts), validation steps (page count verification), and clear stop-and-wait points for user confirmation. The Phase 1 checkpoint is explicitly marked as critical with user response options. | 3 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to external documents. The content that could be split out (full LaTeX template, talk script template, Q&A template, PPTX generation script details, venue color schemes) is all inline, making the file extremely long. However, the section headers provide reasonable navigation within the file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (571 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Commit
700fbe2
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.